Research by
Tobias Braun
VETO
A subtle image cloak that disrupts how modern unified editors attend to a protected reference image.
Fighting Fire with Fire
Protected visual questions steer AI assistants toward controlled wrong answers that form a detectable assignment-level fingerprint.
Obliviate
Guidance-based concept erasure for autoregressive image generators, trained across complete visual-token trajectories.
GEM
A geometric training objective that removes targeted concepts from rectified-flow generators while protecting benign behavior.
Token by Token
Backdoor attacks that use ordinary text triggers to jointly manipulate image and language generation in unified autoregressive models.
Erased but Not Forgotten
A stress test showing how a hidden trigger can survive concept erasure and restore access to supposedly removed content.
DEFAME
A modular, zero-shot system that verifies open-domain image-text claims by dynamically retrieving and reasoning over multimodal evidence.
InFact
A six-stage, retrieval-grounded fact-checker that won the 2024 AVeriTeC shared task and set a strong text-only baseline.